© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12714
    Prev
    Next
    INDEX
    Explanations

    news headline structures, mentioning locations and actions

    oai_token-act-pair · gpt-3.5-turbo

    news articles or reports with strong indicators of location or headlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.71
    fing
    -0.70
     blinding
    -0.70
    aea
    -0.70
    rew
    -0.69
     habit
    -0.68
    unt
    -0.68
     fool
    -0.67
    ocular
    -0.67
     vanity
    -0.67
    POSITIVE LOGITS
     GOODMAN
    0.99
     VIDE
    0.91
     Latest
    0.90
    CLUS
    0.89
     IMAGES
    0.88
     Protesters
    0.84
    HAEL
    0.82
     LAT
    0.81
     RELEASE
    0.80
     Provides
    0.79
    Activations Density 0.388%

    No Known Activations